Search results

1 – 10 of over 6000
To view the access options for this content please click here
Article

Ahmad Mozaffari, Nasser Lashgarian Azad and Alireza Fathi

The purpose of this paper is to demonstrate the applicability of swarm and evolutionary techniques for regularized machine learning. Generally, by defining a proper…

Abstract

Purpose

The purpose of this paper is to demonstrate the applicability of swarm and evolutionary techniques for regularized machine learning. Generally, by defining a proper penalty function, regularization laws are embedded into the structure of common least square solutions to increase the numerical stability, sparsity, accuracy and robustness of regression weights. Several regularization techniques have been proposed so far which have their own advantages and disadvantages. Several efforts have been made to find fast and accurate deterministic solvers to handle those regularization techniques. However, the proposed numerical and deterministic approaches need certain knowledge of mathematical programming, and also do not guarantee the global optimality of the obtained solution. In this research, the authors propose the use of constraint swarm and evolutionary techniques to cope with demanding requirements of regularized extreme learning machine (ELM).

Design/methodology/approach

To implement the required tools for comparative numerical study, three steps are taken. The considered algorithms contain both classical and swarm and evolutionary approaches. For the classical regularization techniques, Lasso regularization, Tikhonov regularization, cascade Lasso-Tikhonov regularization, and elastic net are considered. For swarm and evolutionary-based regularization, an efficient constraint handling technique known as self-adaptive penalty function constraint handling is considered, and its algorithmic structure is modified so that it can efficiently perform the regularized learning. Several well-known metaheuristics are considered to check the generalization capability of the proposed scheme. To test the efficacy of the proposed constraint evolutionary-based regularization technique, a wide range of regression problems are used. Besides, the proposed framework is applied to a real-life identification problem, i.e. identifying the dominant factors affecting the hydrocarbon emissions of an automotive engine, for further assurance on the performance of the proposed scheme.

Findings

Through extensive numerical study, it is observed that the proposed scheme can be easily used for regularized machine learning. It is indicated that by defining a proper objective function and considering an appropriate penalty function, near global optimum values of regressors can be easily obtained. The results attest the high potentials of swarm and evolutionary techniques for fast, accurate and robust regularized machine learning.

Originality/value

The originality of the research paper lies behind the use of a novel constraint metaheuristic computing scheme which can be used for effective regularized optimally pruned extreme learning machine (OP-ELM). The self-adaption of the proposed method alleviates the user from the knowledge of the underlying system, and also increases the degree of the automation of OP-ELM. Besides, by using different types of metaheuristics, it is demonstrated that the proposed methodology is a general flexible scheme, and can be combined with different types of swarm and evolutionary-based optimization techniques to form a regularized machine learning approach.

Details

International Journal of Intelligent Computing and Cybernetics, vol. 7 no. 4
Type: Research Article
ISSN: 1756-378X

Keywords

To view the access options for this content please click here
Article

Yanxia Liu, JianJun Fang and Gang Shi

The sources of magnetic sensors errors are numerous, such as currents around, soft magnetic and hard magnetic materials and so on. The traditional methods mainly use…

Abstract

Purpose

The sources of magnetic sensors errors are numerous, such as currents around, soft magnetic and hard magnetic materials and so on. The traditional methods mainly use explicit error models, and it is difficult to include all interference factors. This paper aims to present an implicit error model and studies its high-precision training method.

Design/methodology/approach

A multi-level extreme learning machine based on reverse tuning (MR-ELM) is presented to compensate for magnetic compass measurement errors by increasing the depth of the network. To ensure the real-time performance of the algorithm, the network structure is fixed to two ELM levels, and the maximum number of levels and neurons will not be continuously increased. The parameters of MR-ELM are further modified by reverse tuning to ensure network accuracy. Because the parameters of the network have been basically determined by least squares, the number of iterations is far less than that in the traditional BP neural network, and the real-time can still be guaranteed.

Findings

The results show that the training time of the MR-ELM is 19.65 s, which is about four times that of the fixed extreme learning algorithm, but training accuracy and generalization performance of the error model are better. The heading error is reduced from the pre-compensation ±2.5° to ±0.125°, and the root mean square error is 0.055°, which is about 0.46 times that of the fixed extreme learning algorithm.

Originality/value

MR-ELM is presented to compensate for magnetic compass measurement errors by increasing the depth of the network. In this case, the multi-level ELM network parameters are further modified by reverse tuning to ensure network accuracy. Because the parameters of the network have been basically determined by least squares, the number of iterations is far less than that in the traditional BP neural network, and the real-time training can still be guaranteed. The revised manuscript improved the ELM algorithm itself (referred to as MR-ELM) and bring new ideas to the peers in the magnetic compass error compensation field.

Details

Sensor Review, vol. 39 no. 1
Type: Research Article
ISSN: 0260-2288

Keywords

To view the access options for this content please click here
Article

Teddy Mantoro, Akeem Olowolayemo, Sunday O. Olatunji, Media A. Ayu, Abu Osman and Tap

Prediction accuracies are usually affected by the techniques and devices used as well as the algorithms applied. This work aims to attempt to further devise a better…

Abstract

Purpose

Prediction accuracies are usually affected by the techniques and devices used as well as the algorithms applied. This work aims to attempt to further devise a better positioning accuracy based on location fingerprinting taking advantage of two important mobile fingerprints, namely signal strength (SS) and signal quality (SQ) and subsequently building a model based on extreme learning machine (ELM), a new learning algorithm for single‐hidden‐layer neural networks.

Design/methodology/approach

Prediction approach to location determination based on historical data has attracted a lot of attention in recent studies, the reason being that it offers the convenience of using previously accumulated location data to subsequently determine locations using predictive algorithms. There have been various approaches to location positioning to further improve mobile user location determination accuracy. This work examines the location determination techniques by attempting to determine the location of mobile users by taking advantage of SS and SQ history data and modeling the locations using the ELM algorithm. The empirical results show that the proposed model based on the ELM algorithm noticeably outperforms k‐Nearest Neighbor approaches.

Findings

WiFi's SS contributes more in accuracy to the prediction of user location than WiFi's SQ. Moreover, the new framework based on ELM has been compared with the k‐Nearest Neighbor and the results have shown that the proposed model based on the extreme learning algorithm outperforms the k‐Nearest Neighbor approach.

Originality/value

A new computational intelligence modeling scheme, based on the ELM has been investigated, developed and implemented, as an efficient and more accurate predictive solution for determining position of mobile users based on location fingerprint data (SS and SQ).

Details

International Journal of Pervasive Computing and Communications, vol. 7 no. 2
Type: Research Article
ISSN: 1742-7371

Keywords

To view the access options for this content please click here
Article

Shujing Zhang, Manyu Zhang, Yujie Cui, Xingyue Liu, Bo He and Jiaxing Chen

This paper aims to propose a fast machine compression scheme, which can solve the problem of low-bandwidth transmission for underwater images.

Abstract

Purpose

This paper aims to propose a fast machine compression scheme, which can solve the problem of low-bandwidth transmission for underwater images.

Design/methodology/approach

This fast machine compression scheme mainly consists of three stages. Firstly, raw images are fed into the image pre-processing module, which is specially designed for underwater color images. Secondly, a divide-and-conquer (D&C) image compression framework is developed to divide the problem of image compression into a manageable size. And extreme learning machine (ELM) is introduced to substitute for principal component analysis (PCA), which is a traditional transform-based lossy compression algorithm. The execution time of ELM is very short, thus the authors can compress the images at a much faster speed. Finally, underwater color images can be recovered from the compressed images.

Findings

Experiment results show that the proposed scheme can not only compress the images at a much faster speed but also maintain the acceptable perceptual quality of reconstructed images.

Originality/value

This paper proposes a fast machine compression scheme, which combines the traditional PCA compression algorithm with the ELM algorithm. Moreover, a pre-processing module and a D&C image compression framework are specially designed for underwater images.

Details

Sensor Review, vol. 39 no. 4
Type: Research Article
ISSN: 0260-2288

Keywords

To view the access options for this content please click here
Article

Smita Rath, Binod Kumar Sahu and Manoj Ranjan Nayak

Forecasting of stock indices is a challenging issue because stock data are dynamic, non-linear and uncertain in nature. Selection of an accurate forecasting model is very…

Abstract

Purpose

Forecasting of stock indices is a challenging issue because stock data are dynamic, non-linear and uncertain in nature. Selection of an accurate forecasting model is very much essential to predict the next-day closing prices of the stock indices. The purpose of this paper is to develop an efficient and accurate forecasting model to predict the next-day closing prices of seven stock indices.

Design/methodology/approach

A novel strategy called quasi-oppositional symbiotic organisms search-based extreme learning machine (QSOS-ELM) is proposed to forecast the next-day closing prices effectively. Accuracy in the prediction of closing price depends on output weights which are dependent on input weights and biases. This paper mainly deals with the optimal design of input weights and biases of the ELM prediction model using QSOS and SOS optimization algorithms.

Findings

Simulation is carried out on seven stock indices, and performance analysis of QSOS-ELM and SOS-ELM prediction models is done by taking various statistical measures such as mean square error, mean absolute percentage error, accuracy and paired sample t-test. Comparative performance analysis reveals that the QSOS-ELM model outperforms the SOS-ELM model in predicting the next-day closing prices more accurately for all the seven stock indices under study.

Originality/value

The QSOS-ELM prediction model and SOS-ELM are developed for the first time to predict the next-day closing prices of various stock indices. The paired t-test is also carried out for the first time in literature to hypothetically prove that there is a zero mean difference between the predicted and actual closing prices.

Details

International Journal of Intelligent Computing and Cybernetics, vol. 12 no. 2
Type: Research Article
ISSN: 1756-378X

Keywords

To view the access options for this content please click here
Article

Di Wu, Huabin Chen, Yinshui He, Shuo Song, Tao Lin and Shanben Chen

The purpose of this paper is to investigate the relationship between the keyhole geometry and acoustic signatures from the backside of a workpiece. It lays a solid…

Abstract

Purpose

The purpose of this paper is to investigate the relationship between the keyhole geometry and acoustic signatures from the backside of a workpiece. It lays a solid foundation for monitoring the penetration state in variable polarity keyhole plasma arc welding.

Design/methodology/approach

The experiment system is conducted on 6-mm-thick aluminum alloy plates based on a dual-sensor system including a sound sensor and a charge coupled device (CCD) camera. The first step is to extract the keyhole boundary from the acquired keyhole images based on median filtering and edge extraction. The second step is to process the acquired acoustic signal to obtain some typical time domain features. Finally, a prediction model based on the extreme learning machine (ELM) technique is built to recognize different keyhole geometries through the acoustic signatures and then identify the welding penetration status according to the recognition results.

Findings

The keyhole geometry and acoustic features after processing can be closely related to dynamic change information of keyhole. These acoustic features can predict the keyhole geometry accurately based on the ELM model. Meanwhile, the predict results also can identify different welding penetration status.

Originality/value

This paper tries to make a foundation work to achieve the monitoring of keyhole condition and penetration status through image and acoustic signals. A useful model, ELM, is built based on these features for predicting the keyhole geometry. Compared with back-propagating neural network and support vector machine, this proposed model is faster and has better generalization performance in the case studied in this paper.

To view the access options for this content please click here
Article

Khaled Mohamed Himair Swhli, Srdjan Jovic, Nebojša Arsic and Petar Spalevic

This paper aims to explore detection of heating load of building by machine learning. Detection of heating load of building is very important in design of buildings due to…

Abstract

Purpose

This paper aims to explore detection of heating load of building by machine learning. Detection of heating load of building is very important in design of buildings due to efficient energy consumption.

Design/methodology/approach

In this study, detection of heating load of building based on effects of dry-bulb temperature, dew-point temperature, radiation, diffuse radiation and wind speed was analyzed. Machine learning approach was implemented for such a purpose.

Findings

The obtained results could be useful for future planning of heating load of buildings. Because the heating load of building is a very nonlinear phenomenon, it is suitable to use machine learning approach to avoid the nonlinearity of the system.

Originality/value

The obtained results could be used effectively in detection of heating load of buildings.

Details

Sensor Review, vol. 38 no. 1
Type: Research Article
ISSN: 0260-2288

Keywords

To view the access options for this content please click here
Article

Emrah Dokur, Cihan Karakuzu, Uğur Yüzgeç and Mehmet Kurban

This paper aims to deal with the optimal choice of a novel extreme learning machine (ELM) architecture based on an ensemble of classic ELM called Meta-ELM structural…

Abstract

Purpose

This paper aims to deal with the optimal choice of a novel extreme learning machine (ELM) architecture based on an ensemble of classic ELM called Meta-ELM structural parameters by using a forecasting process.

Design/methodology/approach

The modelling performance of the Meta-ELM architecture varies depending on the network parameters it contains. The choice of Meta-ELM parameters is important for the accuracy of the models. For this reason, the optimal choice of Meta-ELM parameters is investigated on the problem of wind speed forecasting in this paper. The hourly wind-speed data obtained from Bilecik and Bozcaada stations in Turkey are used. The different number of ELM groups (M) and nodes (Nh) are analysed for determining the best modelling performance of Meta-ELM. Also, the optimal Meta-ELM architecture forecasting results are compared with four different learning algorithms and a hybrid meta-heuristic approach. Finally, the linear model based on correlation between the parameters was given as three dimensions (3D) and calculated.

Findings

It is observed that the analysis has better performance for parameters of Meta-ELM, M = 15 − 20 and Nh = 5 − 10. Also considering the performance metric, the Meta-ELM model provides the best results in all regions and the Levenberg–Marquardt algorithm -feed forward neural network and adaptive neuro fuzzy inference system -particle swarm optimization show competitive results for forecasting process. In addition, the Meta-ELM provides much better results in terms of elapsed time.

Originality/value

The original contribution of the study is to investigate of determination Meta-ELM parameters based on forecasting process.

Details

COMPEL - The international journal for computation and mathematics in electrical and electronic engineering , vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 0332-1649

Keywords

To view the access options for this content please click here
Article

Min Liu, Muzhou Hou, Juan Wang and Yangjin Cheng

This paper aims to develop a novel algorithm and apply it to solve two-dimensional linear partial differential equations (PDEs). The proposed method is based on Chebyshev…

Abstract

Purpose

This paper aims to develop a novel algorithm and apply it to solve two-dimensional linear partial differential equations (PDEs). The proposed method is based on Chebyshev neural network and extreme learning machine (ELM) called Chebyshev extreme learning machine (Ch-ELM) method.

Design/methodology/approach

The network used in the proposed method is a single hidden layer feedforward neural network. The Kronecker product of two Chebyshev polynomials is used as basis function. The weights from the input layer to the hidden layer are fixed value 1. The weights from the hidden layer to the output layer can be obtained by using ELM algorithm to solve the linear equations established by PDEs and its definite conditions.

Findings

To verify the effectiveness of the proposed method, two-dimensional linear PDEs are selected and its numerical solutions are obtained by using the proposed method. The effectiveness of the proposed method is illustrated by comparing with the analytical solutions, and its superiority is illustrated by comparing with other existing algorithms.

Originality/value

Ch-ELM algorithm for solving two-dimensional linear PDEs is proposed. The algorithm has fast execution speed and high numerical accuracy.

Details

Engineering Computations, vol. 38 no. 2
Type: Research Article
ISSN: 0264-4401

Keywords

To view the access options for this content please click here
Article

Liang Chen, Leitao Cui, Rong Huang and Zhengyun Ren

This paper aims to present a bio-inspired neural network for improvement of information processing capability of the existing artificial neural networks.

Abstract

Purpose

This paper aims to present a bio-inspired neural network for improvement of information processing capability of the existing artificial neural networks.

Design/methodology/approach

In the network, the authors introduce a property often found in biological neural system – hysteresis – as the neuron activation function and a bionic algorithm – extreme learning machine (ELM) – as the learning scheme. The authors give the gradient descent procedure to optimize parameters of the hysteretic function and develop an algorithm to online select ELM parameters, including number of the hidden-layer nodes and hidden-layer parameters. The algorithm combines the idea of the cross validation and random assignment in original ELM. Finally, the authors demonstrate the advantages of the hysteretic ELM neural network by applying it to automatic license plate recognition.

Findings

Experiments on automatic license plate recognition show that the bio-inspired learning system has better classification accuracy and generalization capability with consideration to efficiency.

Originality/value

Comparing with the conventional sigmoid function, hysteresis as the activation function enables has two advantages: the neuron’s output not only depends on its input but also on derivative information, which provides the neuron with memory; the hysteretic function can switch between the two segments, thus avoiding the neuron falling into local minima and having a quicker learning rate. The improved ELM algorithm in some extent makes up for declining performance because of original ELM’s complete randomness with the cost of a litter slower than before.

Details

Assembly Automation, vol. 36 no. 2
Type: Research Article
ISSN: 0144-5154

Keywords

1 – 10 of over 6000